examples/AutoTSF_ETTh1/Baseline/exp/exp_main.py

from data_provider.data_factory import data_provider
from utils.tools import EarlyStopping, adjust_learning_rate, visual, test_params_flop
from utils.metrics import metric

import numpy as np
import pandas as pd
import torch
import torch.nn as nn
from torch import optim

import os
import time

import warnings
import matplotlib.pyplot as plt
import numpy as np
warnings.filterwarnings('ignore')

class Exp_Main(object):
    def __init__(self, args,model):
        self.args = args
        self.device = self._acquire_device()
        self.model = model.to(self.device)
        if self.args.use_multi_gpu and self.args.use_gpu:
            model = nn.DataParallel(model, device_ids=self.args.device_ids)

    def _acquire_device(self):
        if self.args.use_gpu:
            os.environ["CUDA_VISIBLE_DEVICES"] = str(
                self.args.gpu) if not self.args.use_multi_gpu else self.args.devices
            device = torch.device('cuda:{}'.format(self.args.gpu))
            print('Use GPU: cuda:{}'.format(self.args.gpu))
        else:
            device = torch.device('cpu')
            print('Use CPU')
        return device

    def _get_data(self, flag):
        data_set, data_loader = data_provider(self.args, flag)
        return data_set, data_loader

    def _select_optimizer(self):
        model_optim = optim.Adam(self.model.parameters(), lr=self.args.learning_rate)
        return model_optim

    def _select_criterion(self):
        criterion = nn.MSELoss()
        return criterion

    def vali(self, vali_data, vali_loader, criterion):
        total_loss = []
        self.model.eval()
        with torch.no_grad():
            for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(vali_loader):
                batch_x = batch_x.float().to(self.device)
                batch_y = batch_y.float()

                batch_x_mark = batch_x_mark.float().to(self.device)
                batch_y_mark = batch_y_mark.float().to(self.device)

                # decoder input
                dec_inp = torch.zeros_like(batch_y[:, -self.args.pred_len:, :]).float()
                dec_inp = torch.cat([batch_y[:, :self.args.label_len, :], dec_inp], dim=1).float().to(self.device)
                # encoder - decoder
                if self.args.use_amp:
                    with torch.cuda.amp.autocast():
                        outputs = self.model(batch_x)
            
                else:
                    outputs = self.model(batch_x)
            
                f_dim = -1 if self.args.features == 'MS' else 0
                outputs = outputs[:, -self.args.pred_len:, f_dim:]
                batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)

                pred = outputs.detach().cpu()
                true = batch_y.detach().cpu()

                loss = criterion(pred, true)

                total_loss.append(loss)
        total_loss = np.average(total_loss)
        self.model.train()
        return total_loss

    def train(self, setting, writer):
        train_data, train_loader = self._get_data(flag='train')
        if not self.args.train_only:
            vali_data, vali_loader = self._get_data(flag='val')
            test_data, test_loader = self._get_data(flag='test')

        path = os.path.join(self.args.checkpoints, setting)
        if not os.path.exists(path):
            os.makedirs(path)

        time_now = time.time()

        train_steps = len(train_loader)
        early_stopping = EarlyStopping(patience=self.args.patience, verbose=True)

        model_optim = self._select_optimizer()
        criterion = self._select_criterion()

        if self.args.use_amp:
            scaler = torch.cuda.amp.GradScaler()

        for epoch in range(self.args.train_epochs):
            iter_count = 0
            train_loss = []

            self.model.train()
            epoch_time = time.time()
            for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(train_loader):
                iter_count += 1
                model_optim.zero_grad()
                batch_x = batch_x.float().to(self.device)

                batch_y = batch_y.float().to(self.device)
                batch_x_mark = batch_x_mark.float().to(self.device)
                batch_y_mark = batch_y_mark.float().to(self.device)

                # decoder input
                dec_inp = torch.zeros_like(batch_y[:, -self.args.pred_len:, :]).float()
                dec_inp = torch.cat([batch_y[:, :self.args.label_len, :], dec_inp], dim=1).float().to(self.device)

                # encoder - decoder
                if self.args.use_amp:
                    with torch.cuda.amp.autocast():
       
                        outputs = self.model(batch_x)
            

                        f_dim = -1 if self.args.features == 'MS' else 0
                        outputs = outputs[:, -self.args.pred_len:, f_dim:]
                        batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)
                        loss = criterion(outputs, batch_y)
                        train_loss.append(loss.item())
                else:
                   
                    outputs = self.model(batch_x)
                    # print(outputs.shape,batch_y.shape)
                    f_dim = -1 if self.args.features == 'MS' else 0
                    outputs = outputs[:, -self.args.pred_len:, f_dim:]
                    batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)
                    loss = criterion(outputs, batch_y)
                    train_loss.append(loss.item())

                if (i + 1) % 100 == 0:
                    print("\titers: {0}, epoch: {1} | loss: {2:.7f}".format(i + 1, epoch + 1, loss.item()))
                    speed = (time.time() - time_now) / iter_count
                    left_time = speed * ((self.args.train_epochs - epoch) * train_steps - i)
                    print('\tspeed: {:.4f}s/iter; left time: {:.4f}s'.format(speed, left_time))
                    iter_count = 0
                    time_now = time.time()

                if self.args.use_amp:
                    scaler.scale(loss).backward()
                    scaler.step(model_optim)
                    scaler.update()
                else:
                    loss.backward()
                    model_optim.step()

            print("Epoch: {} cost time: {}".format(epoch + 1, time.time() - epoch_time))
            train_loss = np.average(train_loss)
            vali_loss = self.vali(vali_data, vali_loader, criterion)
            test_loss = self.vali(test_data, test_loader, criterion)
            print("Epoch: {0}, Steps: {1} | Train Loss: {2:.7f} Vali Loss: {3:.7f} Test Loss: {4:.7f}".format(
                epoch + 1, train_steps, train_loss, vali_loss, test_loss))
            writer.add_scalar("Loss/Train", train_loss, epoch)
            writer.add_scalar("Loss/Validation", vali_loss, epoch)
            writer.add_scalar("Loss/Test", test_loss, epoch)
            early_stopping(vali_loss, self.model, path)

            if early_stopping.early_stop:
                print("Early stopping")
                break

            adjust_learning_rate(model_optim, epoch + 1, self.args)

        best_model_path = path + '/' + 'checkpoint.pth'
        self.model.load_state_dict(torch.load(best_model_path))

        return self.model

    def test(self, setting, test=0):
        test_data, test_loader = self._get_data(flag='test')
        
        if test:
            print('loading model')
            self.model.load_state_dict(torch.load(os.path.join('./checkpoints/' + setting, 'checkpoint.pth')))

        preds = []
        trues = []
        inputx = []
        folder_path = './test_results/' + setting + '/'
        if not os.path.exists(folder_path):
            os.makedirs(folder_path)

        self.model.eval()
        with torch.no_grad():
            for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(test_loader):
                batch_x = batch_x.float().to(self.device)
                batch_y = batch_y.float().to(self.device)

                batch_x_mark = batch_x_mark.float().to(self.device)
                batch_y_mark = batch_y_mark.float().to(self.device)

                # decoder input
                dec_inp = torch.zeros_like(batch_y[:, -self.args.pred_len:, :]).float()
                dec_inp = torch.cat([batch_y[:, :self.args.label_len, :], dec_inp], dim=1).float().to(self.device)
                # encoder - decoder
                if self.args.use_amp:
                    with torch.cuda.amp.autocast():
                        outputs = self.model(batch_x)
                  
                else:
                    outputs = self.model(batch_x)
             

                f_dim = -1 if self.args.features == 'MS' else 0
                # print(outputs.shape,batch_y.shape)
                outputs = outputs[:, -self.args.pred_len:, f_dim:]
                batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)
                outputs = outputs.detach().cpu().numpy()
                batch_y = batch_y.detach().cpu().numpy()

                pred = outputs  # outputs.detach().cpu().numpy()  # .squeeze()
                true = batch_y  # batch_y.detach().cpu().numpy()  # .squeeze()

                preds.append(pred)
                trues.append(true)
                inputx.append(batch_x.detach().cpu().numpy())
                if i % 20 == 0:
                    input = batch_x.detach().cpu().numpy()
                    gt = np.concatenate((input[0, :, -1], true[0, :, -1]), axis=0)
                    pd = np.concatenate((input[0, :, -1], pred[0, :, -1]), axis=0)
                    visual(gt, pd, os.path.join(folder_path, str(i) + '.pdf'))

        if self.args.test_flop:
            test_params_flop((batch_x.shape[1],batch_x.shape[2]))
            exit()
            
        preds = np.concatenate(preds, axis=0)
        trues = np.concatenate(trues, axis=0)

        # result save
        folder_path = './results/' + setting + '/'
        if not os.path.exists(folder_path):
            os.makedirs(folder_path)

        mae, mse, rmse, mape, mspe, rse, corr = metric(preds, trues)
        print('mse:{}, mae:{}'.format(mse, mae))
        f = open("result.txt", 'a')
        f.write(setting + "  \n")
        f.write('mse:{}, mae:{}'.format(mse, mae))
        f.write('\n')
        f.write('\n')
        f.close()
        return [mae, mse]

    def predict(self, setting, load=False):
        pred_data, pred_loader = self._get_data(flag='pred')

        if load:
            path = os.path.join(self.args.checkpoints, setting)
            best_model_path = path + '/' + 'checkpoint.pth'
            self.model.load_state_dict(torch.load(best_model_path))

        preds = []

        self.model.eval()
        with torch.no_grad():
            for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(pred_loader):
                batch_x = batch_x.float().to(self.device)
                batch_y = batch_y.float()
                batch_x_mark = batch_x_mark.float().to(self.device)
                batch_y_mark = batch_y_mark.float().to(self.device)

                # decoder input
                dec_inp = torch.zeros([batch_y.shape[0], self.args.pred_len, batch_y.shape[2]]).float().to(batch_y.device)
                dec_inp = torch.cat([batch_y[:, :self.args.label_len, :], dec_inp], dim=1).float().to(self.device)
                # encoder - decoder
                if self.args.use_amp:
                    with torch.cuda.amp.autocast():
                        outputs = self.model(batch_x)
                    
                else:
                    outputs = self.model(batch_x)
                pred = outputs.detach().cpu().numpy()  # .squeeze()
                preds.append(pred)

        preds = np.array(preds)
        preds = np.concatenate(preds, axis=0)
        if (pred_data.scale):
            preds = pred_data.inverse_transform(preds)
        
        # result save
        folder_path = './results/' + setting + '/'
        if not os.path.exists(folder_path):
            os.makedirs(folder_path)

        np.save(folder_path + 'real_prediction.npy', preds)
        pd.DataFrame(np.append(np.transpose([pred_data.future_dates]), preds[0], axis=1), columns=pred_data.cols).to_csv(folder_path + 'real_prediction.csv', index=False)

        return